Alternatives to shoehorn
200 apps like shoehorn, closest match first.
Top picks
- H

huggingface-local-models
Gethuggingface-local-models is an agent skill for choosing and running language models locally with llama.cpp and GGUF files. It works on CPU, Apple Metal, NVIDIA CUDA and AMD ROCm. The skill searches the Hugging Face Hub for llama.cpp-compati
- H

huggingface-best
Gethuggingface-best is an agent skill for finding the best model for a task. It reads what the user wants the model to do, such as coding, math and reasoning, chat, OCR, retrieval, speech recognition, image classification, multimodal work or a
- I

Inferencer
LaunchInferencer is an app for running large AI language models on your own device. By default all processing happens offline, and no data is sent to the cloud. It is available for iOS, macOS and Android, and the site lists Windows, Linux and web
- N

nemo-mbridge-recipe-recommender
GetRecommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use
- Q

qwencloud-model-selector
GetAn advisor skill from the QwenCloud project that recommends the right Qwen model and parameters. It works in two modes. In interactive advisory mode it asks diagnostic questions and recommends a model from the CDN catalogs. In cross-skill m
- F

fine-tuning-expert
Getfine-tuning-expert is an agent skill from the jeffallan claude-skills collection that helps a coding agent fine-tune large language models and adapt foundation models to specific tasks. It covers configuring parameter-efficient adapters suc
More like shoehorn

tao-finetune-huggingface-model
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an

nemo-mbridge-perf-activation-recompute
Validate and use selective and full activation recompute in Megatron Bridge

tao-port-huggingface-model
Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit
About shoehorn
shoehorn
Make any language model fit your machine
shoehorn is a tool for making a language model fit the memory your machine actually has. Preset quantizations ignore your hardware: you pick one that fits and either waste quality headroom or find out at load time that it does not fit. shoehorn starts from the memory you have, subtracts what inference needs, and solves a per-tensor mixed-precision assignment, so it spends the remaining budget on the tensors where extra precision buys the most quality. The site's example fits a Qwen3 4B model into a 519 MiB weights budget, using 99.998 percent of it. The workflow quantizes a BF16 GGUF file with an importance matrix, then runs the result with llama.cpp, which must be on your PATH. The command line tool includes a local web app, started with shoehorn ui, where you pick a model, press one button and chat. The site also has a Find models page that scans popular Hugging Face models for ones that fit a chosen machine, such as a Mac with 8 to 128 GB or a GPU with 8 to 32 GB of VRAM, and a context length setting. Installation is available through Homebrew, as release downloads for macOS, Linux and Windows, or from source with cargo. The tool is MIT licensed. Its quantizer is written from scratch in Rust, and it produces standard GGUF v3 files that llama.cpp based tools can load.
- Price
- Open source
- Category
- Finance
- Website
- notactuallytreyanastasio.github.io









